Oxford at SemEval-2017 Task 9: Neural AMR Parsing with Pointer-Augmented Attention

Jan Buys, Phil Blunsom


Abstract
We present a neural encoder-decoder AMR parser that extends an attention-based model by predicting the alignment between graph nodes and sentence tokens explicitly with a pointer mechanism. Candidate lemmas are predicted as a pre-processing step so that the lemmas of lexical concepts, as well as constant strings, are factored out of the graph linearization and recovered through the predicted alignments. The approach does not rely on syntactic parses or extensive external resources. Our parser obtained 59% Smatch on the SemEval test set.
Anthology ID:
S17-2157
Volume:
Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)
Month:
August
Year:
2017
Address:
Vancouver, Canada
Editors:
Steven Bethard, Marine Carpuat, Marianna Apidianaki, Saif M. Mohammad, Daniel Cer, David Jurgens
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
914–919
Language:
URL:
https://aclanthology.org/S17-2157
DOI:
10.18653/v1/S17-2157
Bibkey:
Cite (ACL):
Jan Buys and Phil Blunsom. 2017. Oxford at SemEval-2017 Task 9: Neural AMR Parsing with Pointer-Augmented Attention. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 914–919, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Oxford at SemEval-2017 Task 9: Neural AMR Parsing with Pointer-Augmented Attention (Buys & Blunsom, SemEval 2017)
Copy Citation:
PDF:
https://aclanthology.org/S17-2157.pdf
Data
BioLDC2017T10